AIを活用したウェブスクレイピング・クローリング・検索APIのPython SDK

pip install oxylabs-ai-studio

from oxylabs_ai_studio.apps.ai_crawler import AiCrawler

crawler = AiCrawler(api_key="<API_KEY>")
result = crawler.crawl(
    url="https://oxylabs.io",
    user_prompt="Find all pages with proxy products pricing",
    output_format="markdown",
    render_javascript=False,
    return_sources_limit=3,
    geo_location="United States",
)
print("Results:")
for item in result.data:
    print(item, "\n")

from oxylabs_ai_studio.apps.ai_scraper import AiScraper

scraper = AiScraper(api_key="<API_KEY>")
schema = scraper.generate_schema(prompt="want to parse developer, platform, type, price game title, genre (array) and description")
result = scraper.scrape(
    url="https://sandbox.oxylabs.io/products/3",
    output_format="json",
    schema=schema,
    render_javascript=False,
    optimize_content=True,
)
print(result)

from oxylabs_ai_studio.apps.browser_agent import BrowserAgent

browser_agent = BrowserAgent(api_key="<API_KEY>")
schema = browser_agent.generate_schema(prompt="game name, platform, review stars and price")
result = browser_agent.run(
    url="https://sandbox.oxylabs.io/",
    user_prompt="Find if there is game 'super mario odyssey' in the store. If there is, find the price. Use search bar to find the game.",
    output_format="json",
    schema=schema,
)
print(result.data)